Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add radiantlogicinc/fastworkflow --skill author-workflow-skillsgit clone --depth 1 https://github.com/radiantlogicinc/fastworkflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/radiantlogicinc/fastworkflow/author-workflow-skills)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/author-workflow-skills"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/author-workflow-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/author-workflow-skills"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/author-workflow-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00161 | $0.06216 |
| Opus 5.5 | $0.00064 | $0.02486 |
| Sonnet 5.5 | $0.00032 | $0.01243 |
| Haiku 4.5 | $0.00016 | $0.00622 |
Grade A, and why
author-workflow-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing workflow skills
A skill is one Python file, _skills/<name>.py, next to _commands/, written like a command
file. Its Signature describes a job and its Input declares the job's typed arguments,
exactly as a command's; where a command has a ResponseGenerator (it generates a response), a
skill has a PlanGenerator (it generates a plan): each public method is a phase that returns
its steps as text. At run time the skill matcher picks the skill for a request
(workflow_agent.match_skill, from the description and plain_utterances), the planner fills
Input in one typed call (skill_commands.plan_skill_call), the arguments are checked, and
the steps become the agent's numbered plan.
The one-page guide is docs/skill_file_layout.md in the fastworkflow repository (not in the
wheel), with the preview; docs/skill_phases.md covers phases, facts, code-run steps and
answers. The module documentation of fastworkflow.skill (the form),
fastworkflow.skill_commands and fastworkflow.skill_phases (the runtime) ships with the
package and is the source of truth.
Code references below name a module of the fastworkflow package and a symbol in it.
Skill or command?
Write a command (_commands/<name>.py) when |
Write a skill (_skills/<name>.py) when |
|---|---|
it is one action on the application (wraps code, returns an Output) |
a family of requests is answered by the same several commands in a known order (find, open, read, answer) |
| the agent should choose it by intent | the agent keeps getting the order, a value or the answer wrong for that family |
| it needs to read state or call a backend | the job only needs text: PlanGenerator methods build text and must not call a backend or read state (skill_commands module doc) |
A skill adds no capability: every step it writes runs an existing command (checked at load).
A one-command skill is a command with a worse name. Fixed steps with no parameters are
allowed (a PlanGenerator with one method taking no input): the text planner adapts them.
A skill with no parameters may also have phases: every call has the one plan, and the
planner's skill call has no arguments (skill_commands.py skill_from_parts).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago First seen · 310 lines · 161 tokens per session scan A 36e29bb44303
author-workflow-skills is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 16d ago), licensed Apache-2.0. It adds 161 tokens to every session and 6,216 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-24.
author-workflow-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| author-workflow-skillsradiantlogicinc/fastworkflow | Skill | 52 | 16d ago | Apache-2.0 | A | 161 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |